INDEX

Explanations

repeated occurrences of "Mo" associated with a specific context, likely indicating a reference to a person or brand

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cran

-0.16

RICT

-0.15

stellung

-0.15

shiv

-0.15

dim

-0.14

alach

-0.14

ced

-0.13

chaft

-0.13

lopedia

-0.13

branch

-0.13

POSITIVE LOGITS

vrd

0.17

Ð»Ð°ÑĤÑĭ

0.17

onga

0.15

å§¿

0.15

agged

0.15

jam

0.14

éĨ

0.14

otics

0.14

unt

0.14

itional

0.13

Activations Density 0.009%

repeated occurrences of "Mo" associated with a specific context, likely indicating a reference to a person or brand

No Comments

No Known Activations