INDEX

Explanations

references to the word "Mant" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

cards

-0.16

acock

-0.16

addtogroup

-0.15

iesel

-0.15

enthal

-0.15

ãĥ«ãĤ¯

-0.15

evity

-0.15

ackbar

-0.15

preter

-0.14

noop

-0.14

POSITIVE LOGITS

lod

0.16

mant

0.15

OMB

0.15

ality

0.15

ucket

0.14

/generated

0.14

AMED

0.14

uka

0.14

ling

0.14

/mod

0.14

Activations Density 0.014%

references to the word "Mant" and its variations in context

No Comments

No Known Activations