INDEX

Explanations

references to rumors and their psychological implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

longleftrightarrow

-0.15

meleri

-0.14

plist

-0.14

iq

-0.14

ij

-0.13

elas

-0.13

>NN

-0.13

-regexp

-0.13

kiem

-0.13

azine

-0.13

POSITIVE LOGITS

0.15

 Prest

0.14

aker

0.14

uder

0.14

ãĥ¼ãĥ«

0.14

è¾°

0.14

Activations Density 0.179%

references to rumors and their psychological implications

No Comments

No Known Activations