INDEX

Explanations

specific years and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Goldberg

-0.16

ont

-0.15

BASH

-0.15

ieve

-0.14

bit

-0.14

 Cornel

-0.14

gri

-0.13

 curled

-0.13

ato

-0.13

POSITIVE LOGITS

ensis

0.17

statt

0.17

ãĢĳãĢĲ

0.16

eken

0.16

uces

0.15

reesome

0.14

iples

0.14

AssignableFrom

0.14

reshold

0.14

-Sah

0.14

Activations Density 0.029%

specific years and dates

No Comments

No Known Activations